Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4922 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 4516364 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3666. Min Act: -0.1700
Data Index: 3490976 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2416. Min Act: -0.1700
Data Index: 721273 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2416. Min Act: -0.1700
Data Index: 7960010 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2729. Min Act: -0.1700
Data Index: 3695925 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2104. Min Act: -0.1700
Data Index: 5858778 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.1791. Min Act: -0.1700
Data Index: 1445990 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.1479. Min Act: -0.1700
Data Index: 5671337 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.0854. Min Act: -0.1700
Data Index: 420580 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.0854. Min Act: -0.1700
Data Index: 7080710 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.0541. Min Act: -0.1700
Data Index: 4344887 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.0229. Min Act: -0.1700
Data Index: 6917706 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.0229. Min Act: -0.1700
Data Index: 7529109 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6541458 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.9291. Min Act: -0.1700
Data Index: 7922376 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.9604. Min Act: -0.1700
Data Index: 4044012 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.9291. Min Act: -0.1700
Data Index: 1758643 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.9604. Min Act: -0.1700
Data Index: 6112233 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.8979. Min Act: -0.1700
Data Index: 6655435 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4291. Min Range: -6.4291
Max Act: 5.9291. Min Act: -0.1700
Data Index: 3123443 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19